developer_uid: chai_backend_admin
submission_id: chaiml-tl-model-sft-test_v1
model_name: chaiml-tl-model-sft-test_v1
model_group: ChaiML/tl_model_sft_test
status: torndown
timestamp: 2025-05-20T22:27:25+00:00
num_battles: 5252
num_wins: 2621
celo_rating: 1282.5
family_friendly_score: 0.5142
family_friendly_standard_error: 0.0070682156164056
submission_type: basic
model_repo: ChaiML/tl_model_sft_test
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-tl-model-sft-test_v1
is_internal_developer: True
language_model: ChaiML/tl_model_sft_test
model_size: 24B
ranking_group: single
us_pacific_date: 2025-05-20
win_ratio: 0.49904798172124903
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '####', '####\n', 'You:', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-tl-model-sft-test-v1-mkmlizer
Waiting for job on chaiml-tl-model-sft-test-v1-mkmlizer to finish
chaiml-tl-model-sft-test-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-tl-model-sft-test-v1-mkmlizer: ║ _____ __ __ ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ /___/ ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ belonging to: ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-tl-model-sft-test-v1-mkmlizer: ║ ║
chaiml-tl-model-sft-test-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-tl-model-sft-test-v1-mkmlizer: Downloaded to shared memory in 89.848s
chaiml-tl-model-sft-test-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf4aoalf_, device:0
chaiml-tl-model-sft-test-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-tl-model-sft-test-v1-mkmlizer: quantized model in 54.150s
chaiml-tl-model-sft-test-v1-mkmlizer: Processed model ChaiML/tl_model_sft_test in 143.998s
chaiml-tl-model-sft-test-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-tl-model-sft-test-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-tl-model-sft-test-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-tl-model-sft-test-v1
chaiml-tl-model-sft-test-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-tl-model-sft-test-v1/config.json
chaiml-tl-model-sft-test-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-tl-model-sft-test-v1/special_tokens_map.json
chaiml-tl-model-sft-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-tl-model-sft-test-v1/tokenizer_config.json
chaiml-tl-model-sft-test-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-tl-model-sft-test-v1/tokenizer.json
chaiml-tl-model-sft-test-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-tl-model-sft-test-v1/flywheel_model.1.safetensors
chaiml-tl-model-sft-test-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-tl-model-sft-test-v1/flywheel_model.0.safetensors
Failed to get response for submission chaiml-slerpv5-mistral3_24540_v1: ('http://chaiml-slerpv5-mistral3-24540-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40730->127.0.0.1:8080: read: connection reset by peer\n')
chaiml-tl-model-sft-test-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 36.95it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:12, 29.45it/s] Loading 0: 3%|▎ | 12/363 [00:00<00:10, 32.03it/s] Loading 0: 4%|▍ | 16/363 [00:00<00:11, 29.04it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:10, 34.01it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:11, 29.53it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:09, 35.42it/s] Loading 0: 10%|▉ | 36/363 [00:01<00:15, 20.80it/s] Loading 0: 11%|█ | 40/363 [00:01<00:13, 23.43it/s] Loading 0: 12%|█▏ | 44/363 [00:01<00:12, 24.97it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:11, 27.19it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:12, 25.33it/s] Loading 0: 16%|█▌ | 57/363 [00:02<00:10, 28.86it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 26.90it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:10, 27.90it/s] Loading 0: 19%|█▉ | 70/363 [00:02<00:12, 24.28it/s] Loading 0: 20%|██ | 73/363 [00:02<00:13, 20.78it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:10, 25.95it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 24.11it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 25.93it/s] Loading 0: 25%|██▍ | 89/363 [00:03<00:10, 26.62it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:12, 20.94it/s] Loading 0: 27%|██▋ | 99/363 [00:03<00:09, 27.52it/s] Loading 0: 28%|██▊ | 103/363 [00:03<00:09, 26.72it/s] Loading 0: 29%|██▉ | 107/363 [00:04<00:11, 22.74it/s] Loading 0: 31%|███ | 111/363 [00:04<00:09, 25.93it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:10, 23.25it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 28.25it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:09, 26.44it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:08, 28.88it/s] Loading 0: 37%|███▋ | 133/363 [00:05<00:08, 27.65it/s] Loading 0: 38%|███▊ | 138/363 [00:05<00:07, 30.16it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:07, 27.93it/s] Loading 0: 41%|████ | 148/363 [00:05<00:06, 34.46it/s] Loading 0: 42%|████▏ | 152/363 [00:05<00:08, 23.47it/s] Loading 0: 43%|████▎ | 155/363 [00:05<00:08, 23.93it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:10, 20.36it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:07, 27.51it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:07, 27.27it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 30.03it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 28.06it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:06, 28.29it/s] Loading 0: 52%|█████▏ | 187/363 [00:07<00:06, 25.97it/s] Loading 0: 52%|█████▏ | 190/363 [00:07<00:07, 23.22it/s] Loading 0: 53%|█████▎ | 193/363 [00:07<00:07, 23.62it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:07, 23.61it/s] Loading 0: 55%|█████▌ | 200/363 [00:22<00:06, 23.61it/s] Loading 0: 55%|█████▌ | 201/363 [00:22<03:01, 1.12s/it] Loading 0: 56%|█████▌ | 203/363 [00:22<02:30, 1.06it/s] Loading 0: 57%|█████▋ | 208/363 [00:22<01:30, 1.71it/s] Loading 0: 58%|█████▊ | 211/363 [00:22<01:09, 2.18it/s] Loading 0: 59%|█████▉ | 214/363 [00:22<00:52, 2.86it/s] Loading 0: 60%|██████ | 218/363 [00:22<00:35, 4.07it/s] Loading 0: 61%|██████ | 221/363 [00:22<00:27, 5.17it/s] Loading 0: 62%|██████▏ | 224/363 [00:23<00:22, 6.15it/s] Loading 0: 63%|██████▎ | 228/363 [00:23<00:15, 8.64it/s] Loading 0: 64%|██████▎ | 231/363 [00:23<00:13, 10.06it/s] Loading 0: 65%|██████▌ | 237/363 [00:23<00:08, 15.07it/s] Loading 0: 66%|██████▌ | 240/363 [00:23<00:07, 15.87it/s] Loading 0: 68%|██████▊ | 246/363 [00:23<00:05, 20.94it/s] Loading 0: 69%|██████▉ | 250/363 [00:24<00:05, 20.94it/s] Loading 0: 70%|███████ | 255/363 [00:24<00:04, 24.25it/s] Loading 0: 71%|███████ | 258/363 [00:24<00:04, 22.64it/s] Loading 0: 73%|███████▎ | 264/363 [00:24<00:03, 29.49it/s] Loading 0: 74%|███████▍ | 268/363 [00:24<00:04, 23.15it/s] Loading 0: 75%|███████▍ | 271/363 [00:24<00:04, 21.72it/s] Loading 0: 75%|███████▌ | 274/363 [00:25<00:03, 22.93it/s] Loading 0: 76%|███████▋ | 277/363 [00:25<00:03, 23.66it/s] Loading 0: 78%|███████▊ | 282/363 [00:25<00:02, 27.14it/s] Loading 0: 79%|███████▊ | 285/363 [00:25<00:03, 23.80it/s] Loading 0: 80%|████████ | 291/363 [00:25<00:02, 28.39it/s] Loading 0: 81%|████████ | 294/363 [00:25<00:02, 25.13it/s] Loading 0: 82%|████████▏ | 299/363 [00:25<00:02, 28.17it/s] Loading 0: 84%|████████▎ | 304/363 [00:26<00:02, 26.14it/s] Loading 0: 85%|████████▍ | 307/363 [00:26<00:02, 23.30it/s] Loading 0: 85%|████████▌ | 310/363 [00:26<00:02, 24.15it/s] Loading 0: 86%|████████▌ | 313/363 [00:26<00:02, 24.05it/s] Loading 0: 88%|████████▊ | 318/363 [00:26<00:01, 27.40it/s] Loading 0: 88%|████████▊ | 321/363 [00:26<00:01, 25.03it/s] Loading 0: 90%|█████████ | 327/363 [00:27<00:01, 30.09it/s] Loading 0: 91%|█████████ | 331/363 [00:27<00:01, 28.18it/s] Loading 0: 92%|█████████▏| 335/363 [00:27<00:00, 28.61it/s] Loading 0: 93%|█████████▎| 338/363 [00:27<00:00, 27.42it/s] Loading 0: 94%|█████████▍| 341/363 [00:34<00:13, 1.65it/s] Loading 0: 96%|█████████▌| 347/363 [00:34<00:05, 2.76it/s] Loading 0: 96%|█████████▋| 350/363 [00:34<00:03, 3.46it/s] Loading 0: 98%|█████████▊| 355/363 [00:34<00:01, 5.14it/s] Loading 0: 99%|█████████▉| 359/363 [00:34<00:00, 6.67it/s]
Job chaiml-tl-model-sft-test-v1-mkmlizer completed after 176.71s with status: succeeded
Stopping job with name chaiml-tl-model-sft-test-v1-mkmlizer
Pipeline stage MKMLizer completed in 177.26s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-tl-model-sft-test-v1
Waiting for inference service chaiml-tl-model-sft-test-v1 to be ready
Inference service chaiml-tl-model-sft-test-v1 ready after 150.73790431022644s
Pipeline stage MKMLDeployer completed in 151.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4938340187072754s
Received healthy response to inference request in 1.9303524494171143s
Received healthy response to inference request in 1.8179779052734375s
Received healthy response to inference request in 1.915161371231079s
Received healthy response to inference request in 1.835216760635376s
5 requests
0 failed requests
5th percentile: 1.8214256763458252
10th percentile: 1.824873447418213
20th percentile: 1.8317689895629883
30th percentile: 1.8512056827545167
40th percentile: 1.883183526992798
50th percentile: 1.915161371231079
60th percentile: 1.9212378025054933
70th percentile: 1.9273142337799072
80th percentile: 2.0430487632751464
90th percentile: 2.268441390991211
95th percentile: 2.3811377048492433
99th percentile: 2.471294755935669
mean time: 1.9985085010528565
Pipeline stage StressChecker completed in 11.33s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.72s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.73s
Shutdown handler de-registered
chaiml-tl-model-sft-test_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2699.34s
Shutdown handler de-registered
chaiml-tl-model-sft-test_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-tl-model-sft-test_v1 status is now torndown due to DeploymentManager action